FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3189509741> ?p ?o ?g. }

• W3189509741 endingPage "36" @default.
• W3189509741 startingPage "1" @default.
• W3189509741 abstract "Recently, we have witnessed the bloom of neural ranking models in the information retrieval (IR) field. So far, much effort has been devoted to developing effective neural ranking models that can generalize well on new data. There has been less attention paid to the robustness perspective. Unlike the effectiveness, which is about the average performance of a system under normal purpose, robustness cares more about the system performance in the worst case or under malicious operations instead. When a new technique enters into the real-world application, it is critical to know not only how it works in average, but also how would it behave in abnormal situations. So, we raise the question in this work: Are neural ranking models robust? To answer this question, first, we need to clarify what we refer to when we talk about the robustness of ranking models in IR. We show that robustness is actually a multi-dimensional concept and there are three ways to define it in IR: (1) the performance variance under the independent and identically distributed (I.I.D.) setting; (2) the out-of-distribution (OOD) generalizability ; and (3) the defensive ability against adversarial operations. The latter two definitions can be further specified into two different perspectives, respectively, leading to five robustness tasks in total. Based on this taxonomy, we build corresponding benchmark datasets, design empirical experiments, and systematically analyze the robustness of several representative neural ranking models against traditional probabilistic ranking models and learning-to-rank (LTR) models. The empirical results show that there is no simple answer to our question. While neural ranking models are less robust against other IR models in most cases, some of them can still win two out of five tasks. This is the first comprehensive study on the robustness of neural ranking models. We believe the way we study the robustness as well as our findings would be beneficial to the IR community. We will also release all the data and codes to facilitate the future research in this direction." @default.
• W3189509741 created "2021-08-16" @default.
• W3189509741 creator A5006971161 @default.
• W3189509741 creator A5009898523 @default.
• W3189509741 creator A5029998682 @default.
• W3189509741 creator A5052631227 @default.
• W3189509741 creator A5088621320 @default.
• W3189509741 date "2022-12-21" @default.
• W3189509741 modified "2023-10-18" @default.
• W3189509741 title "Are Neural Ranking Models Robust?" @default.
• W3189509741 cites W1979697714 @default.
• W3189509741 cites W1984316072 @default.
• W3189509741 cites W2022871093 @default.
• W3189509741 cites W2031342017 @default.
• W3189509741 cites W2035720976 @default.
• W3189509741 cites W2047221353 @default.
• W3189509741 cites W2079370602 @default.
• W3189509741 cites W2086790337 @default.
• W3189509741 cites W2125825154 @default.
• W3189509741 cites W2136189984 @default.
• W3189509741 cites W2141527331 @default.
• W3189509741 cites W2143331230 @default.
• W3189509741 cites W2149427297 @default.
• W3189509741 cites W2159859920 @default.
• W3189509741 cites W2160039544 @default.
• W3189509741 cites W2161709571 @default.
• W3189509741 cites W2180612164 @default.
• W3189509741 cites W2250539671 @default.
• W3189509741 cites W2536015822 @default.
• W3189509741 cites W2539671052 @default.
• W3189509741 cites W2648699835 @default.
• W3189509741 cites W2739979652 @default.
• W3189509741 cites W2741195357 @default.
• W3189509741 cites W2746600820 @default.
• W3189509741 cites W2783640434 @default.
• W3189509741 cites W2798702669 @default.
• W3189509741 cites W2798989084 @default.
• W3189509741 cites W2799194071 @default.
• W3189509741 cites W2799232306 @default.
• W3189509741 cites W2888491130 @default.
• W3189509741 cites W2899154813 @default.
• W3189509741 cites W2945127593 @default.
• W3189509741 cites W2947415936 @default.
• W3189509741 cites W2954493846 @default.
• W3189509741 cites W2955229766 @default.
• W3189509741 cites W2962700793 @default.
• W3189509741 cites W2962718684 @default.
• W3189509741 cites W2962739339 @default.
• W3189509741 cites W2962818281 @default.
• W3189509741 cites W2962992635 @default.
• W3189509741 cites W2963083752 @default.
• W3189509741 cites W2963859254 @default.
• W3189509741 cites W2963969878 @default.
• W3189509741 cites W2971209824 @default.
• W3189509741 cites W2996851481 @default.
• W3189509741 cites W2998115938 @default.
• W3189509741 cites W3001879867 @default.
• W3189509741 cites W3007157104 @default.
• W3189509741 cites W3011411500 @default.
• W3189509741 cites W3021397474 @default.
• W3189509741 cites W3034408878 @default.
• W3189509741 cites W3035441470 @default.
• W3189509741 cites W3037492894 @default.
• W3189509741 cites W3094612274 @default.
• W3189509741 cites W3098620803 @default.
• W3189509741 cites W3098851962 @default.
• W3189509741 cites W3100149641 @default.
• W3189509741 cites W3102491798 @default.
• W3189509741 cites W3115584932 @default.
• W3189509741 cites W3120496366 @default.
• W3189509741 cites W3152562554 @default.
• W3189509741 cites W3168421658 @default.
• W3189509741 cites W3169965252 @default.
• W3189509741 cites W3198691721 @default.
• W3189509741 cites W4214645465 @default.
• W3189509741 cites W4236789328 @default.
• W3189509741 cites W4251326898 @default.
• W3189509741 doi "https://doi.org/10.1145/3534928" @default.
• W3189509741 hasPublicationYear "2022" @default.
• W3189509741 type Work @default.
• W3189509741 sameAs 3189509741 @default.
• W3189509741 citedByCount "2" @default.
• W3189509741 countsByYear W31895097412023 @default.
• W3189509741 crossrefType "journal-article" @default.
• W3189509741 hasAuthorship W3189509741A5006971161 @default.
• W3189509741 hasAuthorship W3189509741A5009898523 @default.
• W3189509741 hasAuthorship W3189509741A5029998682 @default.
• W3189509741 hasAuthorship W3189509741A5052631227 @default.
• W3189509741 hasAuthorship W3189509741A5088621320 @default.
• W3189509741 hasBestOaLocation W31895097411 @default.
• W3189509741 hasConcept C104317684 @default.
• W3189509741 hasConcept C105795698 @default.
• W3189509741 hasConcept C119857082 @default.
• W3189509741 hasConcept C124101348 @default.
• W3189509741 hasConcept C154945302 @default.
• W3189509741 hasConcept C185592680 @default.
• W3189509741 hasConcept C189430467 @default.
• W3189509741 hasConcept C27158222 @default.

• next